{"total":20,"rows":[{"id":"2509.21317","title":"Interactive Recommendation Agent with Active User Commands","created":"2025-09-25","cited_by_count":10,"area":null},{"id":"2208.13077","title":"SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning","created":"2022-08-27","cited_by_count":8,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2303.09601","title":"Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2310.09123","title":"Automatic Music Playlist Generation via Simulation-based Reinforcement Learning","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2112.13141","title":"On the Unreasonable Efficiency of State Space Clustering in Personalization Tasks","created":"2021-12-24","cited_by_count":3,"area":null},{"id":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2107.06115","title":"A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2210.10631","title":"Simulated Contextual Bandits for Personalization Tasks from Recommendation Datasets","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2506.03324","title":"Optimization of Epsilon-Greedy Exploration","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2108.00151","title":"An Empirical Analysis on Transparent Algorithmic Exploration in Recommender Systems","created":"2021-07-31","cited_by_count":0,"area":null},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2310.05324","title":"Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks","created":"2023-10-09","cited_by_count":0,"area":null}],"next_cursor":null}